Transactions on Emerging Telecommunications Technologies最新文献

{"title":"A Two-Stage Intrusion Detection Ensemble Model for Airborne Networks","authors":"Wenqi Liu,&nbsp;Maohui Zhou,&nbsp;Ruilong Wei,&nbsp;Hongjuan Ge","doi":"10.1002/ett.70418","DOIUrl":"https://doi.org/10.1002/ett.70418","url":null,"abstract":"<div>\u0000 \u0000 <p>Modern aircraft are advancing toward intelligent development, but this connectivity exposes them to new cyber-security threats. Most existing intrusion detection methods are designed for closed-set scenarios and often perform poorly in open-set environments with unknown attacks. We propose a novel open-set intrusion detection system with an undetermined attack detector and a predefined attack classifier. In the first stage, a conditional Gaussian discriminative model is trained using known information and the added conditional Gaussian distribution. Reconstruction error distribution helps distinguish between known and unknown attacks. In the second stage, a gated recurrent unit network integrated with a temporal pattern attention mechanism is used to extract time-series features from the airborne network data. By applying multi-scale convolution operations to the hidden states of the Gated Recurrent Unit, the model effectively captures temporal dependencies and dynamic patterns within network traffic. The proposed method demonstrated promising detection results on MIL-STD-1553 and CICIDS2017, with experimental findings showing that it can detect both known and unknown attacks, thus serving as a viable solution for securing airborne networks.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147683581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secured Authentication and Optimal Key-Based Encryption for Data Privacy Preservation in Mobile Crowd Sensing","authors":"S. Domi Evangeline,&nbsp;G. Usha","doi":"10.1002/ett.70413","DOIUrl":"https://doi.org/10.1002/ett.70413","url":null,"abstract":"<div>\u0000 \u0000 <p>Mobile crowd sensing (MCS) has key strategy for immediately monitoring situations in urban areas and connected vehicles, if the use of a devoted network of sensors is more or less feasible. By exploiting mobile devices and users of smartphones globally, MCS provides an infinite number of unique capabilities. When such a system is extremely beneficial, it requires precise data from sensing and the people who carry them (i.e., users) throughout task supervisory activities such as participant selection and work distribution. People may be hesitant to give data due to privacy concerns. To address and resolve privacy concerns, a data privacy preservation model and anomaly detection are proposed. The major intention of the model is to perform security-based dynamic authentication to achieve privacy preservation in data. Initially, for security purposes, the machine learning algorithm Weighted Probabilistic Neural Network (WPNN) is used, in which the weight optimization is done by Improved Red Panda Optimization (IRPO). Subsequently, with the help of non-attacked network, the dynamic authentication is performed using the Nash Equilibrium (game theory). In further stages, the privacy preservation of data is accomplished by Optimal Key-based Attribute-Based Encryption (OK-ABE). Lastly, the effectiveness of the system is validated and measured across diverse metrics. Therefore, the outstanding results prove that it effectively detects the anomalies and preserves the data.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147683545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to “Spatiotemporal Graph Neural Network-Driven Anomaly Detection for Cooperative Vehicle Messaging in Dense VANET Corridors”","authors":"","doi":"10.1002/ett.70417","DOIUrl":"10.1002/ett.70417","url":null,"abstract":"<p>\u0000 <span>A. Z. Ibrahim</span>, “ <span>Spatiotemporal Graph Neural Network-Driven Anomaly Detection for Cooperative Vehicle Messaging in Dense VANET Corridors</span>,” <i>Transactions on Emerging Telecommunications Technologies</i> <span>37</span>, no. <span>4</span> (<span>2026</span>): e70405, https://doi.org/10.1002/ett.70405.</p><p>In the “Acknowledgements” section, the project number was incorrectly listed as “(PNURSP2026R300).” It should be corrected to “(PNURSP2026R758).” Therefore, the “Acknowledgements” section should read as follows:</p><p>“Princess Nourah bint Abdulrahman University Researchers Supporting Project number (PNURSP2026R758), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.”</p><p>We apologize for this error.</p>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ett.70417","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147683633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient FPGA Accelerator for ECG Signal Classification Using dCViTrN and Optimized Booth Multiplier","authors":"L. Malathi","doi":"10.1002/ett.70410","DOIUrl":"10.1002/ett.70410","url":null,"abstract":"<div>\u0000 \u0000 <p>ECG signal classification is important for the early detection of cardiovascular disorders (CVDs). The current methods have been struggling with the nonlinear complexity of ECG signals, making them inefficient for real-time diagnostic analysis. Thus, this paper proposes a new FPGA-based deep convolutional vision transformer network (dCViTrN) (FPGA-dCViTrN) accelerator to detect different types of arrhythmias. While performing the ECG signal classification process, an unsigned divide, and conquer-based look-up-table (LUT) oriented booth multiplier (UDC-LUT-BM) is used to perform complex mathematical operations of dCViTrN, like multiplication, for minimizing the complexity. Two publicly available datasets, specifically the PTB-XL and MIT-BIH arrhythmia, are used for experimentation. Furthermore, a variety of performance indicators, including accuracy, recall, precision, and F1-score, are utilized to evaluate the deep learning accelerator. In addition, delay, resource utilization, and power consumption are used to assess the hardware complexity. The findings show that the FPGA-dCViTrN design delivers 99.25% and 99.7% classification accuracy on the MIT-BIH and PTB-XL datasets. Overall, this research provides a robust, high-accuracy deep-learning model strengthened by an optimized FPGA architecture, allowing for enhanced, real time ECG classification and assessment in medical diagnostics.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147683181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Lightweight Certificateless Public Encryption With Multi-Keyword Search in IIoT","authors":"Jianhong Zhang,&nbsp;Shijun Zhou","doi":"10.1002/ett.70409","DOIUrl":"10.1002/ett.70409","url":null,"abstract":"<div>\u0000 \u0000 <p>In Industrial IoT ecosystems, resource-constrained devices increasingly rely on searchable encryption (SE) to offload encrypted data to cloud platforms, reducing local computational burdens while preserving data privacy. However, traditional SE technologies struggle to meet the demands of IoT environments featuring large-scale distributed devices, due to cumbersome certificate management and inherent key escrow weaknesses. While certificateless searchable encryption (CLSE) schemes have been proposed to overcome these challenges, most existing solutions remain prone to security flaws and lack support for multi-keyword searches. To address these shortcomings, we present a novel lightweight certificateless public key encryption scheme with multi-keyword search capabilities (CLPSE). Crucially, compared to prior work, our protocol design does not rely on bilinear pairings, but instead employs an elliptic curve algorithm involving only scalar multiplication and addition operations. In addition, to protect the privacy between keywords and ciphertexts, we design a new matrix index structure using the BM25 retrieval algorithm and VFE function. Users can retrieve the corresponding ciphertexts using their trapdoor and threshold, which improves the flexibility of retrieval. Based on this construction, our scheme (CLPSE) is tailored for devices with limited storage and computational capacity. Compared to existing methods, it guarantees the indistinguishability of keyword ciphertexts and trapdoors, while delivering robust protection against both inside and outside keyword guessing attacks (IKGA and OKGA), thereby enhancing keyword security. Experimental results substantiate that our scheme achieves significant improvements in computational and communication efficiency over prior approaches.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147683349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Elegant Privacy Preservation and De-Duplication Model With Elliptic Revocation Cryptography (PPD-ERC) Framework for Cloud Security","authors":"L. Selvam,&nbsp;R. Gomathi,&nbsp;R. Venkatesan","doi":"10.1002/ett.70391","DOIUrl":"10.1002/ett.70391","url":null,"abstract":"<div>\u0000 \u0000 <p>Due to the rapid advancement of communication technology, ensuring cloud data privacy and security is now regarded as one of the most important and difficult tasks. The traditional works are highly concentrated on creating cryptographic models for enhancing cloud system security. However, it encountered issues and problems because of the following factors: increased system overhead, time and storage requirements, complex mathematical operations, and ineffective data handling. In order to guarantee the security, privacy, and access control of cloud data sharing, the proposed work aims to develop a novel framework known as the Privacy Preservation and De-duplication Model with Elliptic Revocation Cryptography (PPD-ERC). This framework includes the entities of Cloud User (CU) (i.e., owner or receiver), Cloud Encryption Server (CES), sub-CES, and Trusted Authority. Here, the lightweight ERC methodology encrypts user data using the private and public key pair. Then, the convergent keys are distributed to the blockchain, and the CU uses the Share algorithm for splitting the convergent keys. The CES validates the user authenticity based on the access controlling mechanism, which allows only the authorized users to obtain the data from server. Moreover, data de-duplication is performed to avoid redundant encrypted data storage in the cloud system, and it increases the processing speed, minimizes the storage space, and optimizes the key generation process. During performance analysis, various evaluation metrics have been used to validate and compare the results of the proposed PPD-ERC mechanism.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147684160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blockchain-Enabled Modified Bi-Directional Recurrent Neural Network for Intelligent Crop Recommendation","authors":"Rishikesh,&nbsp;Ditipriya Sinha","doi":"10.1002/ett.70404","DOIUrl":"10.1002/ett.70404","url":null,"abstract":"<div>\u0000 \u0000 <p>Global food demand is increasing rapidly, while variations in soil characteristics pose persistent challenges to sustainable agriculture. Inappropriate crop selection exacerbates chemical input requirements, accelerates soil degradation, increases cultivation costs, and reduces yield stability. To address these challenges, this paper proposes a data-driven decision-support system that integrates Internet of Things (IoT)-based soil sensing, edge-side data refinement, deep learning for crop recommendation, and blockchain to ensure security. The architecture includes: (i) a <span>Sensor layer</span> with custom-designed nodes to capture soil nutrient; (ii) an <span>Edge layer</span> implementing a Refine-and-Filter (RF) algorithm to eliminate irrelevant data, thereby improving accuracy and reducing communication overhead; and (iii) a <span>Cloud layer</span> employing a private blockchain for secure storage of edge layer data and a modified bidirectional recurrent neural network (modified BRNN), optimized using Gaussian Process Enhanced Hyperband with Neural Tangent Kernel (GPEH-NTK), to generate crop recommendations. Beyond the cloud layer, recommendations are stored on the InterPlanetary File System (IPFS), and their content identifiers (CIDs) are recorded on a separate public (Ethereum) blockchain. The public blockchain also provides decentralized user authentication. Experimental evaluation on public datasets achieved 98.85% accuracy, 98.92% precision, 98.88% recall, and 98.90% F1-score, surpassing state-of-the-art methods. Blockchain analysis confirmed tolerable latency without compromising security and integrity. A field deployment in Darbhanga, Bihar, validated real-time applicability. The findings suggest that the proposed system delivers secure and accurate crop recommendations and offers a viable solution to reduce cultivation costs, enhance yields, and promote sustainable food production.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147683974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Automated Object Detection and Tracking System in Surveillance Aerial Images Using 3D Adaptive Multi-Dilated Yolov8 With Attention Mechanism","authors":"A. R. Shravya,&nbsp;S. Srividhya","doi":"10.1002/ett.70392","DOIUrl":"10.1002/ett.70392","url":null,"abstract":"<div>\u0000 \u0000 <p>Nowadays, the need of detecting targets and performing tracking in aerial images using drones along with power sensor devices has increased. Both drone technology and object detection models provide a major contribution to agricultural irrigation, battlefield reconnaissance, traffic management, and forest patrolling. These kinds of tasks are accomplished with superior accuracy by drone technology. But, the prior techniques faces several challenging problem due to wider image perspective, and enormous tiny objects in the image. Various prior deep learning mechanisms show poor resolution in handling the tiny samples. These kinds of outcomes contribute to poor localization accuracy in the network architecture and also the image fractions are settled with the objects. In order to mitigate these issues, the research leverages a new deep learning-based object detection and tracking approach using surveillance aerial images. Initially, the required surveillance aerial images are gathered by benchmark resources. Further, the garnered images are transferred into the 3D Adaptive Multi-Dilated Yolov8 with Attention Mechanism (3DAMDY-AM) for detecting and tracking the objects in surveillance aerial images. The proposed Improved Lyrebird Optimization Algorithm (ILOA) is employed for optimizing the parameters. At last, the numerical experiments are conducted for the developed model, contrasted with the existing related techniques. The accuracy outcomes of the recommended technique show 95.14%. To ensure better statistical analysis, the best measure of the developed model shows 1.74%, 1.44%, 4.58%, and 1.73% better performance than MTBO-3DAMDY-AM, OOA-3DAMDY-AM, POA-3DAMDY-AM, and LOA-3DAMDY-AM. The mean Average Precision (mAP) measure of the developed approach shows 74.19%, 36.11%, 77.35%, and 80.92% better performance than CNN, N-FINDR, Yolov8, and 3DAMDY-AM, respectively, at the batch size of 8. The significant advancement in the recommended technique guarantees to enhance the system's efficacy and reliability. In summary, the developed model shows a promising outcome, but the work needs to expand on validating real-time data. Moreover, it needs to validate dynamic scalability conditions with diverse surveillance applications in overcrowded scenarios. Further, the multi-data source is also required to improve the model performance on diverse factors like scene times, weather conditions, and locations, respectively.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147683973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cloud Computing With Image Processing Framework for Lung Cancer Diagnosis Using Improved Heuristic-Aided Hybrid Residual Attention Network","authors":"Jayapal Medida,&nbsp;A. B. Pradeep Kumar,&nbsp;Santoshachandra Rao Karanam,&nbsp;Srinivasa Rao Thamanam","doi":"10.1002/ett.70395","DOIUrl":"https://doi.org/10.1002/ett.70395","url":null,"abstract":"<div>\u0000 \u0000 <p>Lung cancer is a primary origin of cancer-based mortality. In the early phases, the recognition of pulmonary cancer can greatly enhance the rate of survival. The manual delineation of lung nodules by medical experts is a tiresome operation. In previous years, the high growth of cloud computing has revolutionized the medical sector to another level. Since lung cancer's causes stay unclear, the prevention process becomes relatively impossible, hence the lung tumor's timely identification is the primary and only way to treat lung cancer. Nowadays, in developed countries, this situation is highly enhanced by employing conventional data sources about lung cancer. Nevertheless, because of the poor data collection approach's synchronization, the gathered data is heterogeneous, and immediately cannot be employed. Therefore, in this developed framework, the cloud-based paradigm for detecting lung cancer disorder utilizing the adaptive deep learning technique is introduced. First, the structural representation of cloud computing is explained and used in the medical application. Further, the necessary images are gathered from the standard data sources. In order to diagnose lung cancer, the novel model is designed and named as Adaptive Hybrid Residual Attention Network (AHRANet), in which the “Convolutional Neural Network” (CNN) is associated with the Densenet. For improving the efficiency, the Random-integer Revamped Hippopotamus Optimization (RRHO) is recommended for optimizing the parameters present in the model. Finally, the efficacy of the system is validated with multiple metrics. In contrast with other techniques, the designed system provides promising results to evince a superior diagnosis of lung cancer ailments.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147568180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Reinforcement Learning–Driven Payoff-Adaptive Game-Theoretic Framework for Secure and Reliable Operation of Mobile Ad Hoc Networks","authors":"Shaik Khader Zelani,&nbsp;K. V. S. S. Ramakrishna,&nbsp;Fatima Asiri,&nbsp;Ahmed Alyahya,&nbsp;Shakila Basheer","doi":"10.1002/ett.70394","DOIUrl":"https://doi.org/10.1002/ett.70394","url":null,"abstract":"<div>\u0000 \u0000 <p>Mobile ad hoc networks (MANETs) are inherently vulnerable to selfish forwarding, collusion, stealthy oscillations, and resource-draining attacks. Due to their decentralized, dynamic, and adversarial nature, existing anomaly-based and deep-learning intrusion detection systems rely on static training distributions and fixed payoff structures. This limits their adaptability under dynamic network conditions. This paper presents a secure and reliable operation of MANETs under adversarial environments. The model integrates a reinforcement learning–driven (RL-driven), payoff-adaptive, three-action game-theoretic (GT) framework. This combination helps learning both the utility structure and the optimal defense strategies for MANET nodes. The model employs online payoff learning, Boltzmann-guided Q-learning, and feature-aware utility estimation to dynamically update security, throughput, energy, and latency trade-offs. Experiments on a large-scale NS-3 mobility dataset (<span></span><math></math> trace snapshots) over 80-node MANETs, 500 rounds, and 10 random seeds demonstrate a strong stability and resilience. The system achieves near-optimal reliability (packet delivery ratio, <span></span><math></math>, low latency <span></span><math></math>, efficient energy usage controlled energy consumption <span></span><math></math> and high average utility <span></span><math></math>. Under seven adversarial threats, the framework consistently restores optimal operation. misreporting impact is reduced, with utility improving from <span></span><math></math>, collusion inflation suppression remains <span></span><math></math>, and regret normalization goes from <span></span><math></math> to <span></span><math></math>. Overall, the proposed GT–RL model provides adaptive equilibrium formation, multi-metric flexibility, and theoretical convergence guarantees for secure MANET operation.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147568181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}